Spatiotemporal LULC Changes and Future Predictions in the Qassim Region, Saudi Arabia, Using Remote Sensing, GIS, and CA-Markov Modelling
Ragab Rabeiy
用遥感、GIS与CA-Markov模型评估沙特Qassim地区2017-2035年土地利用变化与未来
Sentinel-2与Landsat 8 NDVI分类，空间转移与邻近分析，CA
建设用地2025-2035年将增至997 km²，耕地与裸地减少，城镇扩张更依赖道路而非河谷。
可结合耕地流失热点与道路驱动机制，构建干旱区耕地保护优先区与情景预警模型。
预印本以遥感与CA-Markov模拟沙特干旱区土地利用变化，方法完整、验证可靠，但属区域案例且未经同行评审，公共影响有限。
土地利用与土地覆盖（LULC）变化日益影响干旱地区，城市扩张和环境变异性对土地与自然资源形成压力。本研究利用遥感、GIS和CA-Markov模型，评估了沙特阿拉伯卡西姆地区历史与未来的土地利用与土地覆盖变化。采用Sentinel-2影像对2017年、2021年和2025年的七类土地利用与土地覆盖进行分类，并利用Landsat 8衍生的NDVI辅助评估植被变化。同时应用空间转移和邻近性分析，考察土地转变与道路、干谷（wadi）之间的关系。2017年至2025年间，建设用地从387 km²增至685 km²，牧场从1836 km²增至2610 km²。相比之下，裸地从1522 km²减至517 km²，耕地减少70.24 km²。城市扩张主要围绕现有城市发生，与道路的关系强于与干谷的关系，扩张密度从道路250 m范围内的8.3%降至2 km以外的3.9%。NDVI为植被变化提供了额外证据，并部分支持了观测到的牧场增加。随后采用CA-Markov框架，通过模拟2025年建设用地格局并与观测图件比较进行独立评估。验证结果的整体建设用地/非建设用地一致率为96%，精确率为91.57%，F1分数为87.5%。验证后，利用该模型模拟未来土地利用与土地覆盖格局。预计建设用地将在2030年增至约847.4 km²，2035年增至997 km²，而耕地和裸地预计将减少。本研究的主要贡献在于将历史土地利用与土地覆盖转移、空间驱动因素、植被变化、独立模型验证和未来空间预测整合于单一框架内。研究结果可为干旱地区城市增长管理、农用地保护和可持续土地利用规划提供空间信息支持。
Search
Log In Submit
Search
Log in
Join Preprints.org’s OA Week Webinar - October 29, 2026 Register Here
Cite
Add to My List
Share Comments
Download PDF
Version 1
Submitted:
21 October 2026
Posted:
23 October 2026
You are already at the latest version
Subscription
Notify me about updates to this article or when a peer-reviewed version is published.
Subscribe
Preprint
Article
This version is not peer-reviewed.
Spatiotemporal LULC Changes and Future Predictions in the Qassim Region, Saudi Arabia, Using Remote Sensing, GIS, and CA-Markov Modelling
Show more
Version 1
Submitted:
21 October 2026
Posted:
23 October 2026
You are already at the latest version
Abstract
Land use and land cover (LULC) changes are increasingly affecting arid regions, where urban growth and environmental variability place pressure on land and natural resources. This study assessed historical and future LULC changes in the Qassim Region, Saudi Arabia, using remote sensing, GIS, and CA-Markov modelling. Sentinel-2 images were used to classify seven LULC classes for 2017, 2021, and 2025, while Landsat 8-derived NDVI was used to support the assessment of vegetation changes. Spatial transition and proximity analyses were also applied to examine the relationships between land transformation, roads, and wadis. Between 2017 and 2025, built-up land increased from 387 to 685 km², while rangeland increased from 1836 to 2610 km². In contrast, bare ground decreased from 1522 to 517 km², and cropland declined by 70.24 km². Urban expansion occurred mainly around existing cities and showed a stronger relationship with roads than with wadis, with expansion density decreasing from 8.3% within 250 m of roads to 3.9% beyond 2 km. NDVI provided additional evidence of vegetation change and supported part of the observed increase in rangeland. A CA-Markov framework was then used and independently evaluated by simulating the 2025 built-up pattern and comparing it with the observed map. The validation produced an overall built/non-built agreement of 96%, with precision of 91.57% and an F1-score of 87.5%. After validation, the model was used to simulate future LULC patterns. Built-up land is projected to increase to approximately 847.4 km² in 2030 and 997 km² in 2035, while cropland and bare ground are expected to decline. The main contribution of this study is the integration of historical LULC transitions, spatial drivers, vegetation change, independent model validation, and future spatial prediction within a single framework. The findings provide spatial information that can support urban growth management, agricultural land protection, and sustainable land-use planning in arid regions.
Keywords:
land use/land cover (LULC)
;
remote sensing
;
GIS
;
urban expansion
;
NDVI
Subject:
Engineering - Civil Engineering
Copyright: This open access article is published under a Creative Commons CC BY 4.0 license, which permit the free download, distribution, and reuse, provided that the author and preprint are cited in any reuse.
Downloads
32
Views
21
Comments
0
Subscription
Notify me about updates to this article or when a peer-reviewed version is published.
Subscribe
Recommended Preprints
Bilal Jan Haji Muhammad
et al.
,
2026
Karma Tempa
et al.
,
2023
Abduselam Mohammed Ibrahim
et al.
,
2025
Recommended Articles
Salman A. H. Selmy
et al.
Remote Sensing,
2023
Abdullah F. Alqurashi
et al.
Remote Sensing,
2016
Forecasting of Built-Up Land Expansion in a Desert Urban Environment
Shawky Mansour
et al.
Remote Sensing,
2022
Preprints.org is a free preprint server supported by MDPI in Basel, Switzerland.
Contact Us RSS
MDPI Initiatives
Expand MDPI Initiatives
Important Links
Expand Important Links
- Activities
- Advisory Board
- Collections
- How It Works
- Preprints Friendly Journals
- Reading List
- News
- Statistics
Subscribe
Expand Subscribe
Choose an area of interest and we will send you notifications of new preprints at your preferred frequency.
Subscribe
© 2026 MDPI (Basel, Switzerland) unless otherwise stated
Disclaimer
Privacy Settings